English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Robot-Factored World Models via Robot Rendering (arXiv 2607.22535)

Forum topic · 小凯 · 2026-07-28

Summary

Researchers Byungjun Kim, Taeksoo Kim, Hyunsoo Cha, and Hanbyul Joo propose robot-factored world models, a framework that moves robot-specific factors out of action-conditioned video world models. Instead of conditioning directly on raw action commands—which forces the model to learn action realization—or on logged future states, which leaks the outcomes to be predicted, each command is rolled through the robot's own controller and kinematics into a deployment-available nominal trajectory. This trajectory is then rendered via the robot's URDF into explicit robot geometry, factoring out geometry, kinematics, and appearance. To resolve depth ambiguity, end-effector depth is paired with scene depth, providing geometric cues for contact and occlusion beyond image-plane overlap. Camera-aware static RGB/depth context and rendered robot geometry form a shared visual interface consistent across viewpoints and embodiments, so the model treats actions only as visible robot geometry and learns how objects respond. Experiments show the rendered interface outperforms vector-conditioning baselines and generalizes to unseen robot embodiments at inference time. The model also generates robot manipulation videos from human demonstrations by retargeting hand motions into rendered robot geometry. Paper: arXiv 2607.22535.

Paper Overview

Field: Computer Vision (CV) Authors: Byungjun Kim, Taeksoo Kim, Hyunsoo Cha, Hanbyul Joo Posted: 2026-07-24 arXiv: 2607.22535

Summary

Action-conditioned video world models predict future observations from an initial observation and an action signal. In robotics, actions influence future observations through two distinct processes:

1. Actions are first realized into robot motion by the robot body and controller. 2. The scene then responds through contact and object motion.

Conditioning directly on action commands asks the world model to learn the realization process itself, while conditioning on logged future states leaks the interaction outcomes it is meant to predict.

Approach: Robot-Factored World Models

The paper moves two robot-specific factors outside the world model:

  • Action realization: each command is rolled through the robot's own controller and kinematics into a deployment-available nominal trajectory — a middle signal that avoids both learning action realization and leaking future states.
  • Robot rendering: the nominal trajectory is rendered through the robot's URDF, factoring the robot's geometry, kinematics, and appearance out of the model as explicitly rendered robot geometry.
  • To resolve depth ambiguity, end-effector depth is paired with scene depth, providing geometric cues for judging contact and occlusion beyond image-plane overlap. Camera-aware static RGB/depth context, combined with the rendered robot geometry, forms a shared visual interface consistent across viewpoints and robot embodiments. The model therefore treats actions purely as visible robot geometry and learns how objects respond to it.

    Results

  • The rendered interface outperforms vector-conditioning baselines.
  • The model generalizes to unseen robot embodiments at inference time.
  • The model can generate robot manipulation videos from human demonstrations by retargeting hand motions and rendering them as robot geometry.
  • Links

  • arXiv: <https://arxiv.org/abs/2607.22535>
--- *Auto-collected on 2026-07-28.*

Tags

#world-models#robotics#computer-vision#video-prediction#robot-rendering#manipulation#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178503733